Weaviate 1.38 Ships Boost API for Query-Time Rescoring When Hard Filters Are Too Strict
philipvollet · x · 2026-09-03
Weaviate 1.38 introduces the Boost API, addressing the problem of overly strict hard filters: filters exclude results entirely, while Boost only re-ranks after retrieval, keeping other relevant matches in the response.
- How it works: the primary search (vector/hybrid/BM25, etc.) fetches depth candidates, and Boost rescores them in memory, blending with the primary relevance score — no extra shard fan-out, just per-candidate in-memory scoring.
- Condition types: filter conditions (soft WHERE), numeric property values, time decay for recency, and numeric decay around a target value.
- Flexibility: blend up to 20 conditions, use negative weights to demote without excluding, and control the candidate pool with the depth parameter; offset/limit apply after re-sorting.
Official example: searching “yellow armchair,” a filter on instock=true removes all out-of-stock results, whereas Boosting the same condition ranks available products higher while keeping others. Boost works across vector, hybrid, BM25, near-text, near-image and more query types.
More from Infra
- Data center developers are pouring into Iceland for geothermal energy and cold climate — Polymarket · 2026-09-03
- Teacher With 16GB VRAM Hits a Wall: Local LLMs Keep Failing at MCP Tool Use — whakahere · 2026-09-03
- Kimi K3 Draft Collection released: EAGLE-3, DFlash2 and DSpark draft models trained on GB200 — hongyangzh · 2026-09-03
- One bag of almonds' 'waste water' could power 100 ChatGPT queries a day for 385 years — Polymarket · 2026-09-03
- Open-source Marin kicks off 535B/23B MoE pretraining run, fully documented in public — dlwh · 2026-09-03
- Agents spend most of their life on CPU work, not GPU token generation — ai · 2026-09-03